X86_64 monotonic_clock goes backwards
I've noticed some erratic behavior while testing the X86_64 version of monotonic_clock().
While spinning in a loop reading monotonic clock values (pinned to a single cpu) I noticed that the difference between subsequent values occasionally went negative (time going backwards).
I found that in the following code:
this_offset = get_cycles_sync();
/* FIXME: 1000 or 1000000? */
--> offset = (this_offset - last_offset)*1000 / cpu_khz;
}
return base + offset;the offset sometimes turns out to be 0, even though this_offset > last_offset.
The following patch does correct this, and -seems- to be correct. Some reording of code may still be desired.
Dimitri
arch/x86_64/kernel/time.c +2 -2
@@ -281,6 +281,7 @@ static void set_rtc_mmss(unsigned long n* Note: This function is required to return accurate * time even in the absence of multiple timer ticks. */ +static inline unsigned long long cycles_2_ns (unsigned long long cyc);unsigned long long monotonic_clock (void ) {unsigned long seq;
@@ -305,8 +306,7 @@ unsigned long long monotonic_clock(void) base = monotonic_base; }while (read_seqretry (&xtime_lock, seq)); this_offset =get_cycles_sync (); -/* FIXME: 1000 or 1000000? */ - offset = (this_offset - last_offset)*1000 / cpu_khz; + offset =cycles_2_ns (this_offset - last_offset); }return base + offset; }
Quoted 2 lines · Dimitri Sivanich
I've noticed some erratic behavior while testing the
X86_64version ofmonotonic_clock().
Added thanks.
-Andi